合并 chb-replace:C++ 算子替换 Fortran bssn_rhs,添加回退开关与独立 PGO profdata
- 合并 chb-replace 分支,引入 bssn_rhs_c.C / fderivs_c.C / fdderivs_c.C / kodiss_c.C / lopsided_c.C 五个 C++ 算子实现 - 添加 USE_CXX_KERNELS 开关(默认 1),设为 0 可回退到原始 Fortran bssn_rhs.o - TwoPunctureABE 改用独立的 TwoPunctureABE.profdata 而非 default.profdata Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -37,8 +37,27 @@ endif
|
||||
.cu.o:
|
||||
$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
|
||||
|
||||
## TwoPunctureABE uses fixed optimal flags, independent of CXXAPPFLAGS (which may be PGO-instrumented)
|
||||
TP_OPTFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo -Dfortran3 -Dnewc -I${MKLROOT}/include
|
||||
# C rewrite of BSSN RHS kernel and helpers
|
||||
bssn_rhs_c.o: bssn_rhs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
fderivs_c.o: fderivs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
fdderivs_c.o: fdderivs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
kodiss_c.o: kodiss_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
lopsided_c.o: lopsided_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
## TwoPunctureABE uses fixed optimal flags with its own PGO profile, independent of CXXAPPFLAGS
|
||||
TP_PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/TwoPunctureABE.profdata
|
||||
TP_OPTFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
|
||||
-fprofile-instr-use=$(TP_PROFDATA) \
|
||||
-Dfortran3 -Dnewc -I${MKLROOT}/include
|
||||
|
||||
TwoPunctures.o: TwoPunctures.C
|
||||
${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
|
||||
@@ -47,6 +66,16 @@ TwoPunctureABE.o: TwoPunctureABE.C
|
||||
${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
|
||||
|
||||
# Input files
|
||||
|
||||
## Kernel implementation switch (set USE_CXX_KERNELS=0 to fall back to Fortran)
|
||||
ifeq ($(USE_CXX_KERNELS),0)
|
||||
# Fortran mode: no C rewrite files; bssn_rhs.o is included via F90FILES below
|
||||
CFILES =
|
||||
else
|
||||
# C++ mode (default): C rewrite of bssn_rhs and helper kernels
|
||||
CFILES = bssn_rhs_c.o fderivs_c.o fdderivs_c.o kodiss_c.o lopsided_c.o
|
||||
endif
|
||||
|
||||
C++FILES = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
|
||||
cgh.o bssn_class.o surface_integral.o ShellPatch.o\
|
||||
bssnEScalar_class.o perf.o Z4c_class.o NullShellPatch.o\
|
||||
@@ -62,9 +91,9 @@ C++FILES_GPU = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o
|
||||
NullShellPatch2_Evo.o \
|
||||
bssn_gpu_class.o bssn_step_gpu.o bssn_macro.o writefile_f.o
|
||||
|
||||
F90FILES = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
|
||||
F90FILES_BASE = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
|
||||
prolongrestrict_cell.o prolongrestrict_vertex.o\
|
||||
rungekutta4_rout.o bssn_rhs.o diff_new.o kodiss.o kodiss_sh.o\
|
||||
rungekutta4_rout.o diff_new.o kodiss.o kodiss_sh.o\
|
||||
lopsidediff.o sommerfeld_rout.o getnp4.o diff_new_sh.o\
|
||||
shellfunctions.o bssn_rhs_ss.o Set_Rho_ADM.o\
|
||||
getnp4EScalar.o bssnEScalar_rhs.o bssn_constraint.o ricci_gamma.o\
|
||||
@@ -75,6 +104,14 @@ F90FILES = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
|
||||
scalar_rhs.o initial_scalar.o NullEvol2.o initial_null2.o\
|
||||
NullNews2.o tool_f.o
|
||||
|
||||
ifeq ($(USE_CXX_KERNELS),0)
|
||||
# Fortran mode: include original bssn_rhs.o
|
||||
F90FILES = $(F90FILES_BASE) bssn_rhs.o
|
||||
else
|
||||
# C++ mode (default): bssn_rhs.o replaced by C++ kernel
|
||||
F90FILES = $(F90FILES_BASE)
|
||||
endif
|
||||
|
||||
F77FILES = zbesh.o
|
||||
|
||||
AHFDOBJS = expansion.o expansion_Jacobian.o patch.o coords.o patch_info.o patch_interp.o patch_system.o \
|
||||
@@ -87,7 +124,7 @@ TwoPunctureFILES = TwoPunctureABE.o TwoPunctures.o
|
||||
CUDAFILES = bssn_gpu.o bssn_gpu_rhs_ss.o
|
||||
|
||||
# file dependences
|
||||
$(C++FILES) $(C++FILESGPU) $(F90FILES) $(AHFDOBJS) $(CUDAFILES): macrodef.fh
|
||||
$(C++FILES) $(C++FILES_GPU) $(F90FILES) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.fh
|
||||
|
||||
$(C++FILES): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
|
||||
misc.h monitor.h MyList.h Parallel.h MPatch.h prolongrestrict.h\
|
||||
@@ -110,7 +147,7 @@ $(C++FILES_GPU): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h
|
||||
|
||||
$(AHFDOBJS): cctk.h cctk_Config.h cctk_Types.h cctk_Constants.h myglobal.h
|
||||
|
||||
$(C++FILES) $(C++FILES_GPU) $(AHFDOBJS) $(CUDAFILES): macrodef.h
|
||||
$(C++FILES) $(C++FILES_GPU) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.h
|
||||
|
||||
TwoPunctureFILES: TwoPunctures.h
|
||||
|
||||
@@ -119,11 +156,11 @@ $(CUDAFILES): bssn_gpu.h gpu_mem.h gpu_rhsSS_mem.h
|
||||
misc.o : zbesh.o
|
||||
|
||||
# projects
|
||||
ABE: $(C++FILES) $(F90FILES) $(F77FILES) $(AHFDOBJS)
|
||||
$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS)
|
||||
ABE: $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS)
|
||||
$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS)
|
||||
|
||||
ABEGPU: $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
|
||||
$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
|
||||
ABEGPU: $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
|
||||
$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
|
||||
|
||||
TwoPunctureABE: $(TwoPunctureFILES)
|
||||
$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
|
||||
|
||||
Reference in New Issue
Block a user